API Quickstart Guide

Install the SDK

Start by adding the official client library to your project dependencies. This ensures compatibility with our standard endpoints and simplifies request handling.

Use your preferred package manager to install the latest version. The library handles authentication and serialization automatically.

This step is required before you can send any requests to the server.

Configure Base URL and Key

Point your client to our dedicated API gateway using the provided base URL. This directs all traffic to our uncensored model infrastructure.

Set your API key in the environment variable or configuration object. You received this key immediately after signing up via Google or email.

• Base URL: https://api.aizonderfilter.com/v1
• Auth Header: Authorization: Bearer YOUR_API_KEY

Verify your key works by checking the models endpoint.

Make Your First Request

Send a standard chat completion request to receive raw, unfiltered text responses. Our model does not apply standard safety refusals for lawful content.

Use the uncensored model ID for all completions.

The following example demonstrates a basic text generation call.

Copycurl https://api.aizonderfilter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate python code to parse json"}]
  }'

Check the response for the generated text and token usage statistics.

Enable Streaming Responses

For low-latency applications, enable streaming to receive tokens as they are generated. This provides a better user experience for chat interfaces.

Set the stream parameter to true in your request payload.

The server sends Server-Sent Events (SSE) containing partial completions.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aizonderfilter.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Aggregate the chunks to reconstruct the full message. Token usage details appear in the final chunk.

Use JSON Mode and Tools

Enforce structured output or enable function calling for complex logic. Use response_format: {"type": "json_object"} to ensure valid JSON responses.

Define tools in your request to allow the model to call external functions. Specify tool_choice: "auto" for automatic selection.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aizonderfilter.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Parse the tool calls from the response to execute your custom logic. This works reliably with our uncensored model.

Limits, Errors, and Context

Monitor your usage limits to avoid service interruptions. You are allowed 300 requests per minute and 8 concurrent requests per key.

The context window supports 100,000 tokens total. The maximum output per request is 16,000 tokens.

Handle common HTTP errors appropriately:

• 401 Unauthorized: Your API key is invalid or missing.
• 402 Payment Required: Your prepaid credit is exhausted. Top up with crypto to continue.
• 429 Too Many Requests: You have exceeded the rate limit. Wait briefly before retrying.

Errors do not consume your credit balance.

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)